| Name | Shunsuke Saito (齋藤 隼介) |
| Interest | Human digitization algorithms that work in practice |
| {firstname}.{lastname}16 (at) gmail.com |
I am a Research Scientist at Reality Labs Research in Pittsburgh, where I lead the effort on next generation digital humans (foundational model, relighting, faces, hands, full-body, hair, clothing, accessories, and more!). For example, I am one of the core contributers of Codec Avatar 2.0, which was featured in Meta Connect 2022 and Lex Fridman's metaverse interview with MZ. If you are interested in an internship with us, feel free to email/DM me!
|
|
URAvatar: Universal Relightable Gaussian Codec Avatars |
|
|
Manifold Sampling for Differentiable Uncertainty in Radiance Fields |
|
|
Sapiens: Foundation for Human Vision Models |
|
|
Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture |
|
|
Expressive Whole-Body 3D Gaussian Avatar |
|
|
High-Fidelity Modeling of Generalizable Wrinkle Deformation |
|
|
Relightable Gaussian Codec
Avatars |
|
|
URHand: Universal
Relightable Hands |
|
|
GALA: Generating Animatable Layered
Assets
from a Single Scan |
|
|
InterHandGen: Two-Hand Interaction
Generation via Cascaded Reverse Diffusion |
|
|
Drivable 3D Gaussian Avatars |
|
|
Diffusion Shape
Prior for Wrinkle-Accurate Cloth Registration |
|
|
A Dataset of Relighted 3D
Interacting
Hands |
|
|
Diffusion Posterior
Illumination for
Ambiguity-aware
Inverse Rendering |
|
|
Single-Image 3D Human
Digitization with
Shape-guided Diffusion |
|
|
NCHO : Unsupervised Learning for Neural
3D Composition of Humans and Objects |
|
|
CT2Hair: High-Fidelity 3D Hair Modeling
using Computed Tomography |
|
|
RelightableHands: Efficient Neural
Relighting of Articulated Hand Models |
|
|
MEGANE: Morphable Eyeglass and
Avatar Network |
|
|
Dressing
Avatars: Deep Photorealistic Appearance for Physically Simulated
Clothing |
|
|
KeypointNeRF:
Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of
Keypoints |
|
|
AutoAvatar:
Autoregressive Neural Fields for Dynamic Avatar Modeling |
|
|
Neural Strands: Learning
Hair Geometry
and Appearance from Multi-View Images |
|
|
Authentic
Volumetric Avatars From a Phone Scan |
|
|
Drivable
Volumetric Avatars Using Texel-aligned Features |
|
|
COAP:
Compositional Articulated
Occupancy of People |
|
|
Neural Fields in
Visual Computing and Beyond |
|
|
ARCH++:
Animation-Ready Clothed Human Reconstruction Revisited |
|
|
Deep
Relightable
Appearance Models for Animatable Faces |
|
|
SCANimate:
Weakly Supervised Learning of Skinned Clothed Avatar Networks |
|
|
SCALE:
Learning to Model Clothed 3D Humans with a Surface Codec of Articulated Local
Elements |
|
|
Pixel-Aligned
Volumetric Avatars |
|
|
Monocular
Real-Time Volumetric Performance Capture |
|
|
PIFuHD:
Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human
Digitization |
|
|
Learning to Infer
Implicit Surfaces without 3D Supervision |
|
|
PIFu:
Pixel-Aligned Implicit Function for High-Resolution Clothed Human
Digitization |
|
|
SiCloPe:
Silhouette-Based Clothed People |
|
|
3D
Hair Synthesis Using Volumetric Variational Autoencoders |
|
|
paGAN:
Real-time Avatars Using Dynamic Textures |
|
|
High-Fidelity
Facial Reflectance and Geometry Inference From an Unconstrained Image |
|
|
Mesoscopic
Facial Geometry inference Using Deep Neural Networks |
|
|
Avatar
Digitization from a Single Image for Real-Time Rendering |
|
|
Quasi-Developable
Garment Transfer for Animals |
|
|
Outside-in
Monocular IR Camera based HMD Pose Estimation via Geometric
Optimization |
|
|
Learning
Dense Facial Correspondences in Unconstrained Images |
|
|
Realistic
Dynamic Facial Textures From a Single Image Using GANs |
|
|
Production-Level
Facial Performance Capture Using Deep Convolutional Neural Networks |
|
|
Photorealistic
Facial Texture Inference Using Deep Neural Networks |
|
|
Multi-View
Stereo on Consistent Face Topology |
|
|
High-Fidelity
Facial and Speech Animation for VR HMDs |
|
|
Real-Time Facial
Segmentation and Performance Capture from RGB Input |
|
|
Garment
Transfer for Quadruped Characters |
|
|
Computational
Bodybuilding: Anatomically-based Modeling of Human Bodies |
|
|
PatchMove: Patch-based Fast
Image Interpolation with Greedy Bidirectional Correspondence |
|
|
Macroscopic
and Microscopic Deformation Coupling in Up-sampled Cloth Simulation
|
|
|
Character
Transfer:
Example-based individuality retargeting for facial animations |
|
|
Estimating Cloth Simulation Parameter from 3D Cloth Motion
Separating Dynamic from Static Motion |
Shunsuke Saito
Web: www-scf.usc.edu/~saitos/
E-mail: shunsuke.saito16 (at) gmail.com
Technical Paper Reviewer:
ECCV, ICCV, IJCV, SIGGRAPH, CVPR, TPAMI, ToG, AAAI, WACV, 3DV, ACCV, TVCG, Signal Processing, SIGGRAPH ASIA, CGF, PG, Eurographics, etc.
Internship:
MPI Tübingen (2020), FAIR, Adobe Research (2019), Pinscreen (2018), FRL (2017), FOVE (2015), Yahoo! Japan (2012-13)
Talk:
CMU VASC Seminar, Brown VC Seminar, BIRS Workshop, Asiagraphics Webinar (2023), Dagstuhl Seminar (2022), MPI Saarbruecken/Tuebingen, Industrial Light & Magic, Dagstuhl Seminar (2019), University of Tokyo, CMU Graphics Group, VC Symposium (2018), VC/GCAD Symposium, Autodesk Research (2015)
Scholarship and Awards:
Outstanding Reviewer (ICCV2023, 3DV2020,
ACCV2020),
CVPR Best Paper Finalist (2019, 2021),
Super Creator, IPA Exploratory
Software (2015),
ACM Student Research Competition Semi-Finalist (2014),
MIRU Interactive Presentation Award, Okayama, Japan (2014),
UCLA
CSST Scholarship Program $9,036
(2013),
Okuma Memorial Special Scholarship $5,000 (2011)